Timezone: »

 
Poster
Early-stopped neural networks are consistent
Ziwei Ji · Justin Li · Matus Telgarsky

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @

This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is general, and the (optimal) Bayes risk is not necessarily zero. In this setting, it is shown that gradient descent with early stopping achieves population risk arbitrarily close to optimal in terms of not just logistic and misclassification losses, but also in terms of calibration, meaning the sigmoid mapping of its outputs approximates the true underlying conditional distribution arbitrarily finely. Moreover, the necessary iteration, sample, and architectural complexities of this analysis all scale naturally with a certain complexity measure of the true conditional model. Lastly, while it is not shown that early stopping is necessary, it is shown that any classifier satisfying a basic local interpolation property is inconsistent.

Author Information

Ziwei Ji (University of Illinois Urbana-Champaign)
Justin Li (University of Illinois, Urbana Champaign)
Matus Telgarsky (UIUC)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors